Permutation-Invariant Neural Networks for Reinforcement Learning - Hackdot

Re:Permutation-Invariant Neural Networks for Reinforcement L... by gwern on Sunday November 28, 2021 @01:04PM (#29371169)

I think if you wanted to do this at scale, you would prefer Perceiver-IO ( https://arxiv.org/abs/2103.03206#deepmind https://arxiv.org/abs/2107.14795#deepmind ).

[ Parent | on HN ]

There are no comments on this comment yet.